A method, apparatus, device, and medium for constructing three-dimensional models of tumors and blood vessels.

Abstract

This application relates to the field of 3D modeling in the medical field, and particularly to a method, apparatus, device, and medium for constructing a 3D model of tumors and blood vessels. The method involves acquiring tumor images of a patient; importing the tumor images into Mimics Medical 17 software; generating a first mask for the skull region and a second mask for the maxillary artery or internal carotid artery region based on the region growing algorithm of Mimics Medical 17 software; generating a first 3D model containing the skull and blood vessels based on the first and second masks; segmenting and labeling the tumor region along the tumor boundary in the tumor image using a 3D livewire semi-automatic image segmentation algorithm to generate a third mask and a second 3D model; and fusing the first and second 3D models to obtain a fused model. This method enables a comprehensive, three-dimensional, and intuitive assessment of the relationship between tumors and blood vessels in the pterygopalatine fossa and infratemporal fossa.

Description

Technical Field

[0001] This application relates to the field of three-dimensional modeling in the medical field, and in particular to a method, apparatus, device and medium for constructing three-dimensional models of tumors and blood vessels. Background Technology

[0002] The anatomical structures of the pterygopalatine fossa and infratemporal fossa are complex and closely related to major blood vessels. Currently, various surgical zoning and grading systems for tumors in these areas exist to address the surgical challenges. However, existing zoning systems rely on limited imaging data, primarily two-dimensional images, making it difficult to measure the three-dimensional spatial distance between the tumor and important blood vessels and to determine the relative spatial structures. Furthermore, existing systems do not adequately consider vascular protection and control, limiting their applicability to endoscopic surgery for nasal skull base tumors, which is increasingly moving towards three-dimensional, minimally invasive, and bloodless procedures. Additionally, some studies focus on the skull anatomy of healthy individuals, making it difficult to simulate the displacement of anatomical landmarks caused by tumor compression and invasion of this region.

[0003] Therefore, how to comprehensively, three-dimensionally, and intuitively assess the relationship between tumors and blood vessels in the pterygopalatine fossa and infratemporal fossa is an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method for constructing a three-dimensional model of tumors and blood vessels, which can comprehensively, three-dimensionally and intuitively evaluate the relationship between tumors and blood vessels in the pterygopalatine fossa and infratemporal fossa by constructing a three-dimensional model.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a method for constructing a three-dimensional model of a tumor and blood vessels, the method comprising:

[0007] Obtain images of tumors in the patient's pterygopalatine fossa or infratemporal fossa;

[0008] The tumor images are imported into Mimics Medical 17 software. Based on the region growing algorithm of Mimics Medical 17 software, a first mask for the skull region is generated from the CT images in the tumor images. The CTA or...

[0009] MRA images generate a second mask for the maxillary artery or internal carotid artery region;

[0010] A first three-dimensional model containing the skull and blood vessels is generated based on the first and second masks;

[0011] The 3D Livewire semi-automatic image segmentation algorithm was used to segment and label the tumor region along the tumor boundary in the tumor image.

[0012] Generate a third mask;

[0013] A second 3D model containing the tumor is generated based on the third mask;

[0014] The tumor images are fused to obtain a fused image;

[0015] Based on the fused image, the first mask and the second mask are fused using the fusion algorithm of Mimics Medical 17.

[0016] Combined with the third mask, a fusion mask is generated;

[0017] Based on the fusion mask, the first 3D model and the second 3D model are fused to obtain a fused model.

[0018] In a preferred embodiment of this application, the method may be further configured such that, before importing the tumor image into MimicsMedical 17 software, the following steps are performed:

[0019] Images of tumors showing partial postoperative bone defects were excluded.

[0020] In a preferred example of this application, the generation of the third mask may be further configured to include:

[0021] Based on the horizontal, coronal, and sagittal views of the tumor region on CT and / or MRI images, the 3Dlivewire semi-automatic image segmentation algorithm is used to segment and label the tumor region along the tumor boundary of the CT and / or MRI images, generating a third mask.

[0022] In a preferred embodiment of this application, the process of fusing the tumor images to obtain a fused image may be further configured as follows:

[0023] Import the CT, MRI, CTA, or MRA images from the tumor imaging into Mimics Medical 17 software to obtain the imported images;

[0024] Align the imported images until all the imported images have the same reference coordinate system;

[0025] In different imported images, two anatomical landmarks are selected from sagittal, coronal, and horizontal planes, and paired with the anatomical landmarks in different imported images until the anatomical landmarks in different imported images have the same size, position, and orientation.

[0026] The fusion algorithm of Mimics Medical 17 is used to merge the pixel values ​​of different imported images to generate a fused image.

[0027] In a preferred example of this application, it can be further configured to include:

[0028] The fused image and fusion model are calibrated and adjusted.

[0029] In a preferred example of this application, it can be further configured to include:

[0030] The first 3D model, the second 3D model, and the fused model are materialized using 3D printing.

[0031] Secondly, this application provides a device for constructing a three-dimensional model of a tumor and blood vessels, the device comprising:

[0032] The data acquisition module is used to acquire tumor images of the patient's pterygopalatine fossa or infratemporal fossa;

[0033] A mask generation module is used to import the tumor image into Mimics Medical 17 software. Based on the region growing algorithm of Mimics Medical 17 software, a first mask for the skull region is generated from the CT image in the tumor image, and a second mask for the maxillary artery or internal carotid artery region is generated from the CTA or MRA image in the tumor image. The 3D Livewire semi-automatic image segmentation algorithm is used to segment and label the tumor region along the tumor boundary in the tumor image to generate a third mask. The tumor images are fused to obtain a fused image. Based on the fused image, the first mask, the second mask, and the third mask are fused using the fusion algorithm of Mimics Medical 17 to generate a fused mask.

[0034] The model creation module is used to generate a first three-dimensional model containing a skull and blood vessels based on a first mask and a second mask; generate a second three-dimensional model containing a tumor based on a third mask; and fuse the first three-dimensional model and the second three-dimensional model based on the fusion mask to obtain a fused model.

[0035] In a preferred example of this application, it can be further configured to include:

[0036] The image fusion module is used to import CT, MRI, CTA, or MRA images from the tumor imaging into MimicsMedical 17 software to obtain imported images; align the imported images until all imported images have the same reference coordinate system; select two anatomical landmarks from each of the sagittal, coronal, and horizontal planes in different imported images, and pair the anatomical landmarks in different imported images until the anatomical landmarks in different imported images have the same size, position, and orientation; use the fusion algorithm of Mimics Medical 17 to merge the pixel values ​​of the different imported images to generate a fused image.

[0037] Thirdly, this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the tumor and blood vessel three-dimensional model construction method as described in any of the preceding claims.

[0038] Fourthly, this application provides a computer-readable storage medium storing a program, wherein when the program is executed by a processor, it implements the tumor and blood vessel three-dimensional model construction method as described in any of the preceding claims.

[0039] In summary, compared with the prior art, the beneficial effects of the technical solution provided in this application include at least the following:

[0040] This application provides a method for constructing a three-dimensional model of a tumor and blood vessels. The method involves acquiring tumor images of the pterygopalatine fossa or infratemporal fossa of a patient; importing the tumor images into Mimics Medical 17 software; using the region growing algorithm of Mimics Medical 17 software, generating a first mask for the skull region from the CT images in the tumor images, and generating a second mask for the maxillary artery or internal carotid artery region from the CTA or MRA images in the tumor images; generating a first three-dimensional model containing the skull and blood vessels based on the first and second masks; using the 3D Livewire semi-automatic image segmentation algorithm, segmenting and labeling the tumor region along the tumor boundary in the tumor images to generate a third mask; generating a second three-dimensional model containing the tumor based on the third mask; fusing the tumor images to obtain a fused image; using the fusion algorithm of Mimics Medical 17 to fuse the first mask, the second mask, and the third mask to generate a fused mask; and fusing the first three-dimensional model and the second three-dimensional model based on the fused mask to obtain a fused model. By employing multimodal imaging 3D fusion reconstruction technology to construct a 3D model, and fully utilizing the advantages of CT and MRI, the spatial relationship between tumors in the pterygopalatine fossa and infratemporal fossa and the maxillary artery and internal carotid artery can be comprehensively, three-dimensionally, and intuitively assessed from the surgeon's perspective. This provides clinicians with insights for precise intraoperative blood vessel control, aiming to achieve minimally invasive and hemostatic procedures and improve surgical quality. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating a method for constructing a three-dimensional model of a tumor and blood vessels, as provided in one embodiment of this application.

[0042] Figure 2 This is a diagram of an apparatus for constructing a three-dimensional model of a tumor and blood vessels, provided as an embodiment of this application. Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] In one embodiment of this application, a method for constructing a three-dimensional model of a tumor and blood vessels is provided. Please refer to [link to relevant documentation]. Figure 1 As shown, the method includes:

[0045] S100: Obtain images of tumors in the pterygopalatine fossa or infratemporal fossa of the patient;

[0046] S200: Import the tumor image into Mimics Medical 17 software, and based on the region growing algorithm of Mimics Medical 17 software, generate a first mask for the skull region from the CT image in the tumor image, and generate a second mask for the maxillary artery or internal carotid artery region from the CTA or MRA image in the tumor image.

[0047] S300: Generate a first three-dimensional model containing the skull and blood vessels based on the first mask and the second mask;

[0048] S400: Using the 3D Livewire semi-automatic image segmentation algorithm, the tumor region is segmented and labeled along the tumor boundary in the tumor image to generate a third mask;

[0049] S500: Generates a second 3D model containing the tumor based on a third mask;

[0050] S600: Fuse the tumor images to obtain a fused image;

[0051] S700: Based on the fused image, the first mask, the second mask, and the third mask are fused using the fusion algorithm of Mimics Medical 17 to generate a fused mask;

[0052] S800: Based on the fusion mask, the first 3D model and the second 3D model are fused to obtain a fused model.

[0053] In specific implementation, the tumors in the tumor data are primary tumors or tumors involving the pterygopalatine fossa or infratemporal fossa, and the tumor images include at least CTA (CT angiography), i.e., enhanced angiography. The masks in the Mimics Medical 17 software can also be translated as "masks". The specific steps of the region growth algorithm include: before starting region growth, manually selecting one or more seed points located at the target reconstruction site; during region growth, determining whether a pixel or region should grow by setting the maximum and minimum threshold values; starting from the selected seed points, gradually growing and merging adjacent pixels or regions according to the growth rules, growth is usually performed iteratively, with each iteration considering the neighborhood of the current pixel or region and determining whether to continue growing according to the growth rules; region growth continues until a stopping condition is met, such as reaching a preset size or shape, or the pixel intensity or gradient exceeding a set threshold; after region growth is completed, some processing operations can be performed, such as removing boundary noise or holes, smoothing boundaries, or further optimizing the generated 3D model. The first and second 3D models of the tumor are reconstructed layer by layer using masks. The working principle of the 3D Livewire semi-automatic image segmentation algorithm is similar to Photoshop's magnetic lasso tool. Specifically, the user selects pixels in a 2D image that represent the tumor region (generally the tumor edge) as seed points, defining the start of the path. The image's edge information is calculated using an image gradient algorithm. Based on the user-selected seed points, a dynamic programming algorithm is used to find the optimal path from the starting point to the target region. During the path search, the gradient direction and intensity of each node are used to calculate the path cost. For each image node, the cumulative cost to the starting point is calculated. The cumulative cost is calculated by summing the cost of the previous node and the current node, taking into account the distance between nodes. The path with the lowest cumulative cost is obtained through dynamic programming; this path is the segmentation path. The image is then segmented based on the optimal path.

[0054] In this embodiment, a three-dimensional model is constructed by using multimodal image three-dimensional fusion reconstruction technology. By making full use of the advantages of CT and MRI, the spatial positional relationship between tumors in the pterygopalatine fossa and infratemporal fossa and the maxillary artery and internal carotid artery can be comprehensively, three-dimensionally and intuitively assessed from the surgeon's perspective. This provides clinicians with ideas for precise intraoperative blood vessel control, with the aim of achieving minimally invasive and bloodless procedures and improving surgical quality.

[0055] In some embodiments, before importing the tumor images into Mimics Medical 17 software, the following steps are included:

[0056] Images of tumors showing partial postoperative bone defects were excluded.

[0057] In this embodiment, the accuracy of mask generation and 3D modeling in Mimics Medical 17 software is improved.

[0058] In some embodiments, generating the third mask includes:

[0059] Based on the horizontal, coronal, and sagittal views of the tumor region on CT and / or MRI images, the 3Dlivewire semi-automatic image segmentation algorithm is used to segment and label the tumor region along the tumor boundary of the CT and / or MRI images, generating a third mask.

[0060] In practice, the anatomical landmarks include: bony landmarks and bifurcation points of major blood vessels.

[0061] In this embodiment, multimodal images are used for segmentation and annotation of tumor regions, which improves the accuracy of third mask generation.

[0062] In some embodiments, fusing the tumor images to obtain a fused image includes:

[0063] Import the CT, MRI, CTA, or MRA images from the tumor imaging into Mimics Medical 17 software to obtain the imported images;

[0064] Align the imported images until all the imported images have the same reference coordinate system;

[0065] In different imported images, two anatomical landmarks are selected from sagittal, coronal, and horizontal planes, and paired with the anatomical landmarks in different imported images until the anatomical landmarks in different imported images have the same size, position, and orientation.

[0066] The fusion algorithm of Mimics Medical 17 is used to merge the pixel values ​​of different imported images to generate a fused image.

[0067] In this embodiment, multimodal images are used for precise fusion, which improves the accuracy of the fused image and facilitates more accurate fusion of masks and construction of fusion models.

[0068] In some embodiments, it also includes:

[0069] The fused image and fusion model are calibrated and adjusted.

[0070] In practice, the fused images and fused models are calibrated and adjusted. The criteria for successful fusion of the fused images are good overlap of blood vessels and no obvious ghosting at the edges. The criteria for successful fusion of the 3D model are that the vertebral artery completely passes through the transverse foramen of the cervical vertebrae and the internal carotid artery completely passes through the carotid canal at the base of the skull. In addition, two senior physicians with extensive surgical experience and endoscopic anatomy knowledge cross-check and verify the fused images and fused models.

[0071] In this embodiment, the accuracy of the fusion model construction is improved.

[0072] In some embodiments, including:

[0073] The first 3D model, the second 3D model, and the fused model are materialized using 3D printing.

[0074] In this embodiment, the beneficial effects of 3D physical modeling include: doctors and patients can more intuitively observe and understand the condition through the 3D physical model; based on the 3D physical model, doctors can plan and predict surgery, assess the feasibility of surgery, and select appropriate instruments and surgical pathways; the 3D physical model can be used as a medical education and training tool to help medical students and medical staff learn anatomical structures and surgical techniques, making up for the shortcomings of traditional textbooks and 2D images; according to the specific condition of the patient, 3D printing technology can more accurately create individualized tumor, blood vessel, and bone models, providing a more accurate basis for clinical decision-making and surgical plan formulation; doctors can use 3D printed tissue models for simulated surgical training, familiarize themselves with the surgical procedure, become proficient in using instruments, improve surgical skills, and reduce surgical risks; through 3D printing technology, medical devices and implants can be customized according to the individual differences of patients, improving treatment effectiveness and patients' quality of life.

[0075] This application also provides a device for constructing three-dimensional models of tumors and blood vessels; please refer to [link / reference]. Figure 2 As shown, the device includes:

[0076] The data acquisition module 101 is used to acquire tumor images of the patient's pterygopalatine fossa or infratemporal fossa;

[0077] The mask generation module 102 is used to import the tumor image into Mimics Medical 17 software, and based on the region growing algorithm of Mimics Medical 17 software, generate a first mask for the skull region from the CT image in the tumor image, and generate a second mask for the maxillary artery or internal carotid artery region from the CTA or MRA image in the tumor image; use the 3D livewire semi-automatic image segmentation algorithm to segment and label the tumor region along the tumor boundary in the tumor image to generate a third mask; fuse the tumor image to obtain a fused image; based on the fused image, use the fusion algorithm of Mimics Medical 17 to fuse the first mask, the second mask and the third mask to generate a fused mask;

[0078] The model creation module 103 is used to generate a first three-dimensional model containing a skull and blood vessels based on a first mask and a second mask; generate a second three-dimensional model containing a tumor based on a third mask; and fuse the first three-dimensional model and the second three-dimensional model based on the fusion mask to obtain a fused model.

[0079] In some embodiments, the tumor and blood vessel three-dimensional model construction device further includes:

[0080] The image fusion module is used to import CT, MRI, CTA, or MRA images from the tumor imaging into MimicsMedical 17 software to obtain imported images; align the imported images until all imported images have the same reference coordinate system; select two anatomical landmarks from each of the sagittal, coronal, and horizontal planes in different imported images, and pair the anatomical landmarks in different imported images until the anatomical landmarks in different imported images have the same size, position, and orientation; use the fusion algorithm of Mimics Medical 17 to merge the pixel values ​​of the different imported images to generate a fused image.

[0081] This application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the tumor and blood vessel three-dimensional model construction method as described in any of the above embodiments.

[0082] This application also provides a computer-readable storage medium on which a program is stored. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The working process, details, and technical effects of the computer-readable storage medium provided in this embodiment can be found in the above embodiment regarding a method for constructing a three-dimensional model of a tumor and blood vessels, and will not be repeated here.

[0083] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0084] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification. The above embodiments only illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for constructing a three-dimensional model of tumors and blood vessels, characterized in that, include: Obtain images of tumors in the pterygopalatine fossa or infratemporal fossa of the patient; The tumor images are imported into Mimics Medical 17 software. Based on the region growing algorithm of Mimics Medical 17 software, a first mask for the skull region is generated from the CT images in the tumor images, and a second mask for the maxillary artery or internal carotid artery region is generated from the CTA or MRA images in the tumor images. A first three-dimensional model containing the skull and blood vessels is generated based on the first and second masks; Using the 3D Livewire semi-automatic image segmentation algorithm, based on the CT and / or MRI images in the tumor images, the tumor region is segmented and labeled along the tumor boundary in the CT and / or MRI images to generate a third mask; A second 3D model containing the tumor is generated based on the third mask; The tumor images are fused to obtain a fused image; Based on the fused image, the first mask, the second mask, and the third mask are fused using the fusion algorithm of Mimics Medical 17 to generate a fused mask; Based on the fusion mask, the first 3D model and the second 3D model are fused to obtain a fused model.

2. The method for constructing a three-dimensional model of tumors and blood vessels according to claim 1, characterized in that, Before importing the tumor images into Mimics Medical 17 software, the following steps are included: Images of tumors showing partial postoperative bone defects were excluded.

3. The method for constructing a three-dimensional model of tumors and blood vessels according to claim 1, characterized in that, Generating the third mask includes: Based on the horizontal, coronal, and sagittal views of the tumor region on CT and / or MRI images, a 3D Livewire semi-automatic image segmentation algorithm is used to segment and label the tumor region along the tumor boundary of the CT and / or MRI images, generating a third mask.

4. The method for constructing a three-dimensional model of tumors and blood vessels according to claim 1, characterized in that, The fusion of the tumor images to obtain a fused image includes: Import the CT, MRI, CTA, or MRA images from the tumor imaging into Mimics Medical 17 software to obtain the imported images; Align the imported images until all the imported images have the same reference coordinate system; In different imported images, two anatomical landmarks are selected from sagittal, coronal, and horizontal planes, and paired with the anatomical landmarks in different imported images until the anatomical landmarks in different imported images have the same size, position, and orientation. The fusion algorithm of Mimics Medical 17 is used to merge the pixel values ​​of different imported images to generate a fused image.

5. The method for constructing a three-dimensional model of tumors and blood vessels according to claim 4, characterized in that, include: The fused image and fusion model are calibrated and adjusted.

6. The method for constructing a three-dimensional model of tumors and blood vessels according to claim 1, characterized in that, include: The first 3D model, the second 3D model, and the fused model are materialized using 3D printing.

7. A device for constructing a three-dimensional model of a tumor and blood vessels, characterized in that, include: The data acquisition module is used to acquire tumor images of the patient's pterygopalatine fossa or infratemporal fossa; A mask generation module is used to import the tumor images into Mimics Medical 17 software. Based on the region growing algorithm of Mimics Medical 17 software, a first mask for the skull region is generated from the CT images in the tumor images, and a second mask for the maxillary artery or internal carotid artery region is generated from the CTA or MRA images in the tumor images. Using the 3Dlivewire semi-automatic image segmentation algorithm, the tumor region is segmented and labeled along the tumor boundary in the CT and / or MRI images in the tumor images to generate a third mask. The tumor images are then fused to obtain a fused image. Based on the fused image, the first mask, the second mask, and the third mask are fused using the fusion algorithm of Mimics Medical 17 to generate a fused mask. The model creation module is used to generate a first three-dimensional model containing a skull and blood vessels based on a first mask and a second mask; generate a second three-dimensional model containing a tumor based on a third mask; and fuse the first three-dimensional model and the second three-dimensional model based on the fusion mask to obtain a fused model.

8. The three-dimensional model construction device for tumors and blood vessels according to claim 7, characterized in that, Also includes: The image fusion module is used to import CT, MRI, CTA, or MRA images from the tumor imaging into Mimics Medical 17 software to obtain imported images; align the imported images until all imported images have the same reference coordinate system; in different imported images, select two anatomical landmarks from sagittal, coronal, and horizontal planes, and pair the anatomical landmarks in different imported images until the anatomical landmarks in different imported images have the same size, position, and orientation; use the fusion algorithm of Mimics Medical 17 to merge the pixel values ​​of the different imported images to generate a fused image.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for constructing a three-dimensional model of a tumor and blood vessels as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program, wherein when the program is executed by a processor, it implements the method for constructing a three-dimensional model of a tumor and blood vessels as described in any one of claims 1 to 6.

Images